Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4194. Min Act: -0.0000

Data Index: 682701 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.5668. Min Act: -0.0000

Data Index: 255794 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.5668. Min Range: -3.5668

Max Act: 3.4154. Min Act: -0.0000

Data Index: 29168 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.8002. Min Act: -0.0000

Data Index: 67733 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.8788. Min Act: -0.0000

Data Index: 1123564 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.7714. Min Act: -0.0000

Data Index: 1115847 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.7457. Min Act: -0.0000

Data Index: 528966 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.8900. Min Act: -0.0000

Data Index: 388016 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.8676. Min Act: -0.0000

Data Index: 614212 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.5886. Min Act: -0.0000

Data Index: 272384 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.7818. Min Act: -0.0000

Data Index: 270546 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.6678. Min Act: -0.0000

Data Index: 959526 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.6744. Min Act: -0.0000

Data Index: 761319 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.4762. Min Act: -0.0000

Data Index: 972151 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.3489. Min Act: -0.0000

Data Index: 778393 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.4794. Min Act: -0.0000

Data Index: 958683 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.5806. Min Act: -0.0000

Data Index: 151367 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.3157. Min Act: -0.0000

Data Index: 899485 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.5001. Min Act: -0.0000

Data Index: 536191 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.5668. Min Range: -3.5668

Max Act: 2.3657. Min Act: -0.0000

Data Index: 501791 (C4 (Web Text))

Max Activating Token Index: 409